Classifier rules in data mining - A Survey

This paper focuses on the functionalities of the various classifier rules in data mining. It presents an idea about how classifier rules are working over the given data sets. It also emancipates the variations induced by the classifier rules for obtaining the desired optimum classification. Classifier rules are the protocols which are implied over the data sets in order to obtain a highly comprehensive and accurate results. The two division of classification prediction are perfect and imperfect test. In perfect test the population or the elements of the dataset fall exactly into the target class whereas in imperfect test there are some errors in the prediction of the target class. Such perfect and imperfect tests are carried out by means of which classification rule assigns the elements of the training population set to any one of the classes. This enhances the users to get a classified output for any type of massive data which was provided as an input.